© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5718
    Prev
    Next
    INDEX
    Explanations

    words used in scientific and technical journal articles

    oai_token-act-pair · gemini-2.0-flash

    scientific terminology related to biological and mechanical properties

    np_token-act-pair-logits · gpt-4o-mini

    scientific properties and structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -1.01
     يتيمه
    -0.85
    хьтан
    -0.59
    KommentareTeilen
    -0.58
    EDEFAULT
    -0.58
     pinulongan
    -0.57
    getMenuInflater
    -0.56
    ')")
    -0.56
    ^(@)
    -0.56
     Normdatei
    -0.55
    POSITIVE LOGITS
     оригіналу
    0.80
     properties
    0.56
     AppCompatTheme
    0.55
     Properties
    0.54
     conclusions
    0.51
    ellini
    0.50
    mitten
    0.47
     characteristics
    0.47
     features
    0.45
     arran
    0.45
    Activations Density 3.951%

    No Known Activations